INDEX
Explanations
comparative adjectives relating to age and size
New Auto-Interp
Negative Logits
findpost
-0.55
Wide
-0.52
исленность
-0.52
-0.49
let
-0.47
su
-0.46
High
-0.46
val
-0.46
say
-0.45
プト
-0.45
POSITIVE LOGITS
rungsseite
1.01
Hauptartikel
0.88
leſs
0.86
wiſe
0.84
Lighter
0.84
quieter
0.82
myſelf
0.80
ſtill
0.80
+#+
0.78
sharper
0.78
Activations Density 0.149%